Max (@max_grev) header
Max (@max_grev) profile picture

Experiments in health, endurance, and tech. Building @FeanorLabs.

San Francisco, CA
Joined May 2018
Photo by Max (@max_grev)Photo by Max (@max_grev)Photo by Max (@max_grev)Photo by Max (@max_grev)Photo by Max (@max_grev)Photo by Max (@max_grev)Photo by Max (@max_grev)Photo by Max (@max_grev)Photo by Max (@max_grev)Photo by Max (@max_grev)
Before we finally get to AGI, any software that isn't extremely niche or enterprise-focused will live inside agents from the big labs. So, there are essentially only a few options left: - sell to / build for the agents - lean heavily into anything irl - experiences, communities - build a physical product that's hard to replicate - build a beloved personality (then you can sell anything because the product is you) - obsess over craft/taste building extremely niche products (vibe coders could never) - join one of the main labs (if you can’t beat them, join them) - invest in anything above and do whatever you want with your free time
1
6
251
And most of these stay relevant even after AGI
1
37
A walkie-talkie for all your agents--Claude, Codex, Grok Bot, Dot, and Muse--is now open source.
I built a fun way to talk to all your agents (Grok @bot, Claude, Codex, Dot, @Muse, and Pi) from anywhere. Even while you're touching grass. Meet Maestro, a handheld agent orchestrator powered by an ESP32-S3. Pick a conversation, hold a button, and talk. Hear the reply or read it on the screen. Each agent gets its own pixel character. Maestro buzzes when one replies. It works even when your laptop is offline, so you can leave it behind and go outside.
4
3
157
Trying to reinvent the agent interface because the brain fatigue from reading model outputs all day is so real that I basically stopped reading books.
2
9
285
"A rabbit hole of epic proportions because I can do whatever I want to do" podcast episodes are the best kind of podcast episode.
NEW podcast episode is up! "Lucky #888 — My Tour of Designing Luck in China, Japan, and Korea" For episode #888, I couldn’t resist going down a rabbit hole about the number eight. Join me for a nerdy tour of China, Japan, and Korea, including a million-dollar license plate, disappearing hotel floors, a casino room designed around one gambler’s birthday, and much, much more. Please enjoy!
1
1
12
10,050
Finished the Kernel Track in 93rd place overall, with a 2.314× speedup over SGLang on the decode layer (and 63rd on bf16_proj at 1.600×, but that doesn't count). Not quite where I expected myself to finish, but considering I didn't know what a kernel was going in, I'll take it.
3
7
868
Fun bts numbers: ~9,000 recorded GPU tests: 8,894 measured configuration/shape test entries and 700 judge runs across all five tracks. 435 lab files, 117 work folders, 93 assembled decode files and 917 commits.
2
34
Highest leaderboard ranks achieved during the challenge: - #2, #6, and #8 on bf16_proj (before I learned it didn't count toward the overall ranking); - #3 on the prefill layer (but that was judgemaxxed); - #69 on the decode layer.
1
83
I keep seeing these "No on G," "Yes on E," "Maybe on X" signs all over SF, and can't help but wonder, perhaps naively: 1. What's the point of electing government *representatives*, employing ~35,000 government workers, and spending ~$20,000 per capita if general population is then asked to make these decisions? 2. Who has the time and willingness to thoughtfully research all these props? Either the unemployed, actively involved in politics, or people generally not known for their acute decision-making. What am I missing here.
1
1
95
Something feels a bit iffy about California prop 38. Doing a popular vote proposed by a 3 person non-profit that gives said non profit $4.2B from the public! I hope Gary is great and knows how to spend $4.2B well because it’s done.
16
Some of my recent App Store header animations
5
359
Lots of updates! And yes, I'm still having too much fun with these opus-5.5 motion design videos.
🆕 What's new in v4.1.8: ◦ Improved and simplified the keyboard dictation flow. ◦ Fully optimized for iPhone Duo, including the keyboard. ◦ Significantly improved keyboard autocorrect and typing performance. ◦ Keyboard’s Fix Grammar, Translate, and Paraphrase features can now handle longer texts. ◦ You can now customize the keyboard writing tools, reorder them, and remove the ones you don’t use. Settings → Keyboard → Writing Tools. ◦ Now you can adjust how long the microphone stays ready for your next voice dictation: 1, 15, or 30 minutes, or 1, 3, or 8 hours. Settings → Magic Dictation → Keep Mic Ready. ◦ New keyboard theme: Auri Clear. ◦ Improved the Simplified Chinese 10-key and QWERTY keyboards. ◦ Improved Ask Auri with feedback options. ◦ Added emoji search in Chinese and Korean to their respective keyboards. ◦ Quality-of-life improvements across the app. ◦ Fewer bugs and improved performance. Thank you for your feedback, feature requests, and bug reports!
2
3
147
What you read on X vs reality. Thank you, Apple.
1
144
Sundays are for long runs
1
3
178
Down to #51 overnight, back up to #8 at 1.5233x. What a rollercoaster.
1
310
Back in the top 10. (can’t believe I somehow overtook the legend I was learning ML from back in 2018)
44
🫡
Plugin discovery on ChatGPT leads to massive adoption opportunity. Open ecosystems will win.
1
2
194
OpenAI won. It took 15 days from submission to approval, while Muse isn't even in review yet.
1
20
pluginmaxxing
10